Create atlas/splitmerge Module (#1756)

* Add atlas/splitmerge module

* Finish the tests for atlas/splitmerge

* Prettier

* Update modules/atlas/splitmerge/meta.yml

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

* Remove curly brackets from meta.yml parameters

For single-file outputs, as reviewed

* Lintung: Remove trailing white-space

Co-authored-by: James A. Fellows Yates <jfy133@gmail.com>

modules/atlas/splitmerge/main.nf

@@ -0,0 +1,36 @@
+process ATLAS_SPLITMERGE {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::atlas=0.9.9" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/atlas:0.9.9--h082e891_0':
+        'quay.io/biocontainers/atlas:0.9.9--h082e891_0' }"
+
+    input:
+    tuple val(meta), path(bam), path(bai), path(read_group_settings), path(blacklist)
+
+    output:
+    tuple val(meta), path("*_mergedReads.bam"), path("*.txt.gz"), emit: data
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def optional = blacklist ? 'blacklist=${blacklist}' : ''
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    atlas \\
+        task=splitMerge bam=${bam} \\
+        readGroupSettings=${read_group_settings}\\
+        $optional \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        atlas: \$((atlas 2>&1) | grep Atlas | head -n 1 | sed -e 's/^[ \t]*Atlas //')
+    END_VERSIONS
+    """
+}

modules/atlas/splitmerge/meta.yml

@@ -0,0 +1,70 @@
+name: "atlas_splitmerge"
+description: split single end read groups by length and merge paired end reads
+keywords:
+  - split
+  - merge
+  - bam
+  - read group
+tools:
+  - "atlas":
+      description: "ATLAS, a suite of methods to accurately genotype and estimate genetic diversity"
+      homepage: "https://bitbucket.org/wegmannlab/atlas/wiki/Home"
+      documentation: "https://bitbucket.org/wegmannlab/atlas/wiki/Home"
+      tool_dev_url: "https://bitbucket.org/wegmannlab/atlas"
+      doi: "10.1101/105346"
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - bam:
+      type: file
+      description: Single input BAM file.
+      pattern: "*.bam"
+  - bai:
+      type: file
+      description: The BAI file for the input BAM file
+      pattern: "*.bai"
+  - read_group_setting:
+      type: file
+      description: |
+        TXT file containing the split and merge settings for
+        each readgroup. Each line consist of one readgroup,
+        single/double identifier and the maximum cycle number
+        of the sequencer. e.g. "RG1 single 100"
+      pattern: "*.txt"
+  - blacklist:
+      type: file
+      description: |
+        blacklist.txt (optional), A txt file with blacklisted read names
+        that should be ignored and just written to file, each on a new line
+      pattern: "*.txt"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+
+  - bam:
+      type: file
+      description: A BAM file with suffix_mergedReads.bam
+      pattern: "*_mergedReads.bam"
+
+  - filelist:
+      type: file
+      description: A file listing all reads that were filtered out in the merging process with suffix_ignoredReads.txt.gz
+      pattern: "*.txt.gz"
+
+authors:
+  - "@merszym"

tests/config/pytest_modules.yml

@@ -78,6 +78,10 @@ ataqv/ataqv:
   - modules/ataqv/ataqv/**
   - tests/modules/ataqv/ataqv/**
 
+atlas/splitmerge:
+  - modules/atlas/splitmerge/**
+  - tests/modules/atlas/splitmerge/**
+
 bakta:
   - modules/bakta/**
   - tests/modules/bakta/**

tests/config/test_data.config

@@ -235,7 +235,9 @@ params {
                 mitochon_standin_recalibrated_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam"
                 mitochon_standin_recalibrated_sorted_bam_bai   = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/mitochon_standin.recalibrated.sorted.bam.bai"
                 
-                test3_single_end_markduplicates_sorted_bam       = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test3.single_end.markduplicates.sorted.bam"
+                test3_single_end_markduplicates_sorted_bam     = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/test3.single_end.markduplicates.sorted.bam"
+
+                read_group_settings_txt                        = "${test_data_dir}/genomics/homo_sapiens/illumina/bam/read_group_settings.txt"
 
                 test_paired_end_sorted_cram                      = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram"
                 test_paired_end_sorted_cram_crai                 = "${test_data_dir}/genomics/homo_sapiens/illumina/cram/test.paired_end.sorted.cram.crai"

tests/modules/atlas/splitmerge/main.nf

@@ -0,0 +1,15 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { ATLAS_SPLITMERGE } from '../../../../modules/atlas/splitmerge/main.nf'
+
+//MAIN
+workflow test_atlas_splitmerge {
+    meta = [ id:'test', single_end:false ]
+    bam = file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true)
+    bai = file(params.test_data['homo_sapiens']['illumina']['test_paired_end_sorted_bam_bai'], checkIfExists: true)
+    settings = file(params.test_data['homo_sapiens']['illumina']['read_group_settings_txt'], checkIfExists: true)
+
+    ATLAS_SPLITMERGE ( [meta, bam, bai, settings, []] )
+}

tests/modules/atlas/splitmerge/nextflow.config

@@ -0,0 +1,5 @@
+process {
+    withName: ATLAS_SPLITMERGE {
+        publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    }
+}

tests/modules/atlas/splitmerge/test.yml

@@ -0,0 +1,11 @@
+- name: atlas splitmerge test_atlas_splitmerge
+  command: nextflow run tests/modules/atlas/splitmerge -entry test_atlas_splitmerge -c tests/config/nextflow.config
+  tags:
+    - atlas
+    - atlas/splitmerge
+  files:
+    - path: output/atlas/test.paired_end.sorted_ignoredReads.txt.gz
+      md5sum: 9b64c47313d2de89c26790f713707ee6
+    - path: output/atlas/test.paired_end.sorted_mergedReads.bam
+    - path: output/atlas/versions.yml
+      md5sum: 11735bec9c2f4b395b987fd00d4e4294